High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
MCP gateway and API proxy for agent traffic
Lunar.dev provides a mediation layer for outbound API use in agent and application workflows. It combines a proxy for traffic control with an MCP aggregator so you can centralize access, watch usage, and apply governance rules.
Builders who want to put one governed gateway in front of the APIs their agents use.
You can control, observe, and shape agent API calls without wiring each service separately.
What it does
Live traffic visibility
Shows latency, errors, cost, and token usage across outbound API and agent calls.
Policy enforcement
Lets you control tool access and apply fine-grained rules to agent traffic.
Traffic shaping
Supports rate limits, retries, priority queues, and circuit breakers.
MCP aggregation
Combines multiple MCP servers behind one gateway for simpler access and management.
Example clients and interceptors
Includes sample consumer apps and a TypeScript interceptor for trying the gateway in real flows.
README
Welcome to Lunar.dev
Lunar.dev is an open-source platform for managing, governing and optimizing third-party API consumption across applications and AI agent workloads at scale.
Consumption Management for the AI Era
As AI agents and autonomous workflows increasingly rely on external APIs, there's a growing need for a mediation layer that acts as a central aggregation point between applications, agents, and the services they depend on.
Lunar.dev provides that layer—serving as a unified API Gateway for AI, delivering:
- Live API Traffic Visibility: Get real-time metrics on latency, errors, cost, and token usage across all outbound traffic, including LLM and agent calls.
- AI-Aware Policy Enforcement: Control tool access, throttle agent actions, and govern agentic traffic with fine-grained rules.
- Advanced Traffic Shaping: Apply rate limits, retries, priority queues, and circuit breakers to manage load and ensure reliability.
- Cost & Performance Optimization: Identify waste, smooth traffic peaks, and reduce overuse of costly APIs through smart gateway policies.
- Centralized MCP Aggregation: Streamline operations by consolidating multiple MCP servers into a single gateway, enhancing security, observability, and management.
Choose Your Path
Lunar.dev is composed of two major components:
- Lunar Proxy – our core API gateway and control layer
- Lunar MCPX – a zero-code aggregator for multiple MCP servers with unified API access
Explore the one that fits your needs—or use both for a full-stack solution.
Open Source at the Core
This project was born out of the need for a more robust, production-ready approach to managing third-party APIs. It remains open-source at its core and free for non-production/personal use. For production environments, we offer advanced features through guided onboarding and platform tiers; visit our website or reach out directly for more information
Files in the repo
- .github
- example-consumer-app
- interceptors
- mcpx
- proxy
- readme-files
- .dcignore
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- LICENSE
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。